MX2021014462A - Red neuronal para la clasificacion y la recuperacion de busquedas. - Google Patents

Red neuronal para la clasificacion y la recuperacion de busquedas.

Info

Publication number
MX2021014462A
MX2021014462A MX2021014462A MX2021014462A MX2021014462A MX 2021014462 A MX2021014462 A MX 2021014462A MX 2021014462 A MX2021014462 A MX 2021014462A MX 2021014462 A MX2021014462 A MX 2021014462A MX 2021014462 A MX2021014462 A MX 2021014462A
Authority
MX
Mexico
Prior art keywords
query
document
term
terms
calculated
Prior art date
Application number
MX2021014462A
Other languages
English (en)
Inventor
Corbin Louis Rosset
Bhaskar Mitra
David Anthony Hawking
Nicholas Eric Craswell
Fernando Diaz
Emine Yilmaz
Original Assignee
Microsoft Technology Licensing Llc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Microsoft Technology Licensing Llc filed Critical Microsoft Technology Licensing Llc
Publication of MX2021014462A publication Critical patent/MX2021014462A/es

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/903—Querying
    • G06F16/9038—Presentation of query results
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/951—Indexing; Web crawling techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/31—Indexing; Data structures therefor; Storage structures
    • G06F16/313—Selection or weighting of terms for indexing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/335—Filtering based on additional data, e.g. user or group profiles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

En la presente se describe un mecanismo para utilizar una red neuronal para identificar y clasificar los resultados de búsqueda. Un modelo de aprendizaje de máquina se entrena al convertir datos de entrenamiento que comprenden entradas de consulta-documento en entradas de término de consulta-documento. Las entradas de término de consulta-documento se utilizan para entrenar el modelo de aprendizaje de máquina. Se identifica un conjunto de términos de consulta. Los términos de consulta se pueden derivar de un historial de consultas. El modelo de aprendizaje de máquina entrenado se utiliza para calcular las puntuaciones de clasificación de documentos para los términos de consulta y las puntuaciones resultantes se almacenan en un índice de término-documento precalculado. Una consulta para buscar el índice de documento se descompone en sus términos constituyentes y una puntuación de clasificación de documento agregada se calcula a partir de una suma ponderada de las puntuaciones de clasificación de documento que corresponden a los términos de consulta individual. Debido a que el índice de término-documento se puede precalcular, se puede descargar para proporcionar capacidades de búsqueda de aprendizaje profundo en un entorno computacionalmente limitado.
MX2021014462A 2019-05-27 2020-03-25 Red neuronal para la clasificacion y la recuperacion de busquedas. MX2021014462A (es)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US16/423,081 US11615149B2 (en) 2019-05-27 2019-05-27 Neural network for search retrieval and ranking
PCT/US2020/024540 WO2020242566A1 (en) 2019-05-27 2020-03-25 Neural network for search retrieval and ranking

Publications (1)

Publication Number Publication Date
MX2021014462A true MX2021014462A (es) 2022-01-06

Family

ID=70334078

Family Applications (1)

Application Number Title Priority Date Filing Date
MX2021014462A MX2021014462A (es) 2019-05-27 2020-03-25 Red neuronal para la clasificacion y la recuperacion de busquedas.

Country Status (7)

Country Link
US (2) US11615149B2 (es)
EP (1) EP3959625A1 (es)
CN (1) CN113906417A (es)
AU (1) AU2020283383A1 (es)
CA (1) CA3138920A1 (es)
MX (1) MX2021014462A (es)
WO (1) WO2020242566A1 (es)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021005433A1 (ja) * 2019-07-05 2021-01-14 株式会社半導体エネルギー研究所 読解支援システム及び読解支援方法
US11176330B2 (en) * 2019-07-22 2021-11-16 Advanced New Technologies Co., Ltd. Generating recommendation information
WO2021152715A1 (ja) * 2020-01-29 2021-08-05 日本電信電話株式会社 学習装置、検索装置、学習方法、検索方法及びプログラム
US11556573B2 (en) 2020-05-29 2023-01-17 Adobe Inc. Semantic cluster formation in deep learning intelligent assistants
US11868413B2 (en) * 2020-12-22 2024-01-09 Direct Cursus Technology L.L.C Methods and servers for ranking digital documents in response to a query
CN113515620A (zh) * 2021-07-20 2021-10-19 云知声智能科技股份有限公司 电力设备技术标准文档排序方法、装置、电子设备和介质
US11562400B1 (en) * 2021-09-23 2023-01-24 International Business Machines Corporation Uplift modeling
CN115329169B (zh) * 2022-06-27 2023-10-20 海南电网有限责任公司信息通信分公司 一种基于深度神经模型的档案归档计算方法
CN116991980B (zh) * 2023-09-27 2024-01-19 腾讯科技（深圳）有限公司 文本筛选模型训练方法及相关方法、装置、介质及设备

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007002820A2 (en) * 2005-06-28 2007-01-04 Yahoo! Inc. Search engine with augmented relevance ranking by community participation
US7685091B2 (en) 2006-02-14 2010-03-23 Accenture Global Services Gmbh System and method for online information analysis
US7822752B2 (en) 2007-05-18 2010-10-26 Microsoft Corporation Efficient retrieval algorithm by query term discrimination
US10783451B2 (en) 2016-10-12 2020-09-22 Accenture Global Solutions Limited Ensemble machine learning for structured and unstructured data
US10783141B2 (en) * 2018-04-19 2020-09-22 International Business Machines Corporation Natural language processing social-based matrix refactorization
US20200183884A1 (en) * 2018-12-06 2020-06-11 Microsoft Technology Licensing, Llc Content-aware search suggestions

Also Published As

Publication number Publication date
US11615149B2 (en) 2023-03-28
EP3959625A1 (en) 2022-03-02
CA3138920A1 (en) 2020-12-03
AU2020283383A1 (en) 2021-11-18
US20200380038A1 (en) 2020-12-03
US20230229710A1 (en) 2023-07-20
WO2020242566A1 (en) 2020-12-03
CN113906417A (zh) 2022-01-07

Similar Documents

Publication Publication Date Title
MX2021014462A (es) Red neuronal para la clasificacion y la recuperacion de busquedas.
Iyyer et al. A neural network for factoid question answering over paragraphs
CN106598937B (zh) 用于文本的语种识别方法、装置和电子设备
RU2018132848A (ru) Способ и система для расширения поисковых запросов с целью ранжирования результатов поиска
RU2015141340A (ru) Способ (варианты) и система (варианты) создания модели прогнозирования и определения точности модели прогнозирования
KR101220557B1 (ko) 사람의 활동 지식 데이터베이스를 이용한 모바일 어플리케이션 검색 방법 및 시스템
MX2019014606A (es) Ascenso coordinado personalizado para registros de datos clasificados.
WO2019226399A3 (en) Skill discovery for computerized personal assistant
JP2010257488A5 (es)
MX2020009283A (es) Clasificacion y puntuacion de motor de busqueda.
CN109032375A (zh) 候选文本排序方法、装置、设备及存储介质
CN109165380A (zh) 一种神经网络模型训练方法及装置、文本标签确定方法及装置
RU2013146871A (ru) Способ уточнения результатов поиска в базе данных
MX2020009560A (es) Clasificacion y presentacion de resultados de motor de busqueda con base en modelos de clasificacion especificos de categoria.
GB2581464A (en) Supporting evidence retrieval for complex answers
CN106960001A (zh) 一种检索词的实体链接方法及系统
CN102831177A (zh) 语句纠错方法及其系统
EP3090393A1 (en) Ranking of discussion threads in a question-and-answer forum
MX349273B (es) Busqueda de voz y respuestas basada en relevancia.
CN109710732B (zh) 信息查询方法、装置、存储介质和电子设备
CN111090664A (zh) 基于神经网络的高仿人多模式对话方法
CN109740158A (zh) 一种文本语义解析方法及装置
CN108304373A (zh) 语义词典的构建方法、装置、存储介质和电子装置
CN110096572A (zh) 一种样本生成方法、装置及计算机可读介质
PH12021550937A1 (en) Information providing system, information providing method, and data structure of knowledge data